Merge pull request #504 from AidanTilgner/bugfix/puppeteer-chromium-not-found

fix: docker should install chromium and puppeteer should be no sandbox

Dockerfile

@@ -8,7 +8,12 @@ FROM node:18-alpine
 RUN apk add --update libc6-compat python3 make g++
 # needed for pdfjs-dist
 RUN apk add --no-cache build-base cairo-dev pango-dev
+
+# Install Chromium
+RUN apk add --no-cache chromium
+
 ENV PUPPETEER_SKIP_DOWNLOAD=true
+ENV PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser
 
 WORKDIR /usr/src/packages
 

docker/Dockerfile

@@ -6,7 +6,12 @@ RUN apk add --no-cache git
 RUN apk add --no-cache python3 py3-pip make g++
 # needed for pdfjs-dist
 RUN apk add --no-cache build-base cairo-dev pango-dev
+
+# Install Chromium
+RUN apk add --no-cache chromium
+
 ENV PUPPETEER_SKIP_DOWNLOAD=true
+ENV PUPPETEER_EXECUTABLE_PATH=/usr/bin/chromium-browser
 
 # You can install a specific version like: flowise@1.0.0
 RUN npm install -g flowise

packages/components/nodes/documentloaders/Puppeteer/Puppeteer.ts

@@ -73,7 +73,12 @@ class Puppeteer_DocumentLoaders implements INode {
 
         const puppeteerLoader = async (url: string): Promise<any> => {
             let docs = []
-            const loader = new PuppeteerWebBaseLoader(url)
+            const loader = new PuppeteerWebBaseLoader(url, {
+                launchOptions: {
+                    args: ['--no-sandbox'],
+                    headless: 'new'
+                }
+            })
             if (textSplitter) {
                 docs = await loader.loadAndSplit(textSplitter)
             } else {